Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks

• URL: http://arxiv.org/abs/2412.02357v1
• Date: Tue, 03 Dec 2024 10:27:04 GMT
• Title: Dynamic Prompt Middleware: Contextual Prompt Refinement Controls for Comprehension Tasks
• Abstract summary: This study investigates user needs for control over AI-generated explanations in comprehension tasks.<n>We implement two prompt approaches: Dynamic Prompt Refinement Control (Dynamic PRC) and Static Prompt Refinement Control (Static PRC)<n>We evaluate the impact of these approaches on user control of AI responses for crafting better explanations.
• Score: 15.808343159772066
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this barrier by assisting in prompt construction, but barriers remain for users in expressing adequate control so that they can receive AI-responses that match their preferences. We conduct a formative survey (n=38) investigating user needs for control over AI-generated explanations in comprehension tasks, which uncovers a trade-off between standardized but predictable support for prompting, and adaptive but unpredictable support tailored to the user and task. To explore this trade-off, we implement two prompt middleware approaches: Dynamic Prompt Refinement Control (Dynamic PRC) and Static Prompt Refinement Control (Static PRC). The Dynamic PRC approach generates context-specific UI elements that provide prompt refinements based on the user's prompt and user needs from the AI, while the Static PRC approach offers a preset list of generally applicable refinements. We evaluate these two approaches with a controlled user study (n=16) to assess the impact of these approaches on user control of AI responses for crafting better explanations. Results show a preference for the Dynamic PRC approach as it afforded more control, lowered barriers to providing context, and encouraged exploration and reflection of the tasks, but that reasoning about the effects of different generated controls on the final output remains challenging. Drawing on participant feedback, we discuss design implications for future Dynamic PRC systems that enhance user control of AI responses. Our findings suggest that dynamic prompt middleware can improve the user experience of generative AI workflows by affording greater control and guide users to a better AI response.

Related papers

• Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods [56.14010017381489]
  This paper argues that the machine learning community must pivot from ad-hoc XAI methods toward addressing foundational & structural challenges.<n>We conclude by outlining a practical checklist designed to shift XAI toward a more human-centered, action-oriented paradigm.
  arXiv  Detail & Related papers  (2026-06-18T21:46:20Z)
• DocOS: Towards Proactive Document-Guided Actions in GUI Agents [54.27655693145045]
  textbfDocOS is a benchmark designed to assess document-guided problem solving in fully interactive environments.<n>Experiments reveal that agents struggle to reliably locate relevant information during proactive search and frequently fail to faithfully ground retrieved instructions into precise actions.
  arXiv  Detail & Related papers  (2026-05-18T08:36:04Z)
• Steering LLMs via Scalable Interactive Oversight [74.12746881843044]
  Large Language Models increasingly automate complex, long-horizon tasks such as emphvibe coding, a supervision gap has emerged.<n>It presents a critical challenge in scalable oversight: enabling humans to responsibly steer AI systems on tasks that surpass their own ability to specify or verify.
  arXiv  Detail & Related papers  (2026-02-04T04:52:00Z)
• Bridging Gulfs in UI Generation through Semantic Guidance [16.245249868262178]
  We develop a system that enables users to specify semantics, visualize relationships, and extract how semantics are reflected in generated UIs.<n>A comparative user study suggests that our approach enhances users' perceived control over intent expression, outcome interpretation, and facilitates more predictable, iterative refinement.
  arXiv  Detail & Related papers  (2026-01-27T04:01:53Z)
• RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering [62.63376387138257]
  We propose a plug-and-play intervention framework that adaptively steers large language models (LLMs) reasoning in activation space.<n>RISER constructs a library of reusable reasoning vectors and employs a lightweight Router to dynamically compose them for each input.<n>The Router is optimized via reinforcement learning under task-level rewards, activating latent cognitive primitives in an emergent and compositional manner.
  arXiv  Detail & Related papers  (2026-01-14T08:04:33Z)
• Interactive Recommendation Agent with Active User Commands [35.77744269746443]
  We introduce the Interactive Recommendation Feed (IRF), a pioneering paradigm that enables natural language commands within mainstream recommendation feeds.<n>Unlike traditional systems that confine users to passive implicit behavioral influence, IRF empowers active explicit control over recommendation policies through real-time linguistic commands.<n> RecBot shows significant improvements in both user satisfaction and business outcomes.
  arXiv  Detail & Related papers  (2025-09-25T15:38:27Z)
• Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models [54.85405423240165]
  We introduce Interactive Reasoning, an interaction design that visualizes chain-of-thought outputs as a hierarchy of topics.<n>We implement interactive reasoning in Hippo, a prototype for AI-assisted decision making in the face of uncertain trade-offs.
  arXiv  Detail & Related papers  (2025-06-30T10:00:43Z)
• NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search [108.42163676745085]
  We envision NExT-Search, a next-generation paradigm designed to reintroduce fine-grained, process-level feedback into generative AI search.<n> NExT-Search integrates two complementary modes: User Debug Mode, which allows engaged users to intervene at key stages; and Shadow User Mode, where a personalized user agent simulates user preferences.
  arXiv  Detail & Related papers  (2025-05-20T17:59:13Z)
• Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User [117.82681846559909]
  Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations. We propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs.
  arXiv  Detail & Related papers  (2025-04-29T06:37:30Z)
• Understanding Learner-LLM Chatbot Interactions and the Impact of Prompting Guidelines [9.834055425277874]
  This study investigates learner-AI interactions through an educational experiment in which participants receive structured guidance on effective prompting. To assess user behavior and prompting efficacy, we analyze a dataset of 642 interactions from 107 users. Our findings provide a deeper understanding of how users engage with Large Language Models and the role of structured prompting guidance in enhancing AI-assisted communication.
  arXiv  Detail & Related papers  (2025-04-10T15:20:43Z)
• Interactive Explanations for Reinforcement-Learning Agents [10.17968794823259]
  We present ASQ-IT -- an interactive explanation system that presents video clips of the agent acting in its environment based on queries given by the user that describe temporal properties of behaviors of interest. Our approach is based on formal methods: queries in ASQ-IT's user interface map to a fragment of Linear Temporal Logic over finite traces (LTLf), which we developed, and our algorithm for query processing is based on automata theory.
  arXiv  Detail & Related papers  (2025-04-07T18:00:50Z)
• Collaborative Instance Navigation: Leveraging Agent Self-Dialogue to Minimize User Input [54.81155589931697]
  We propose a new task, Collaborative Instance Navigation (CoIN), with dynamic agent-human interaction during navigation.<n>To address CoIN, we propose a novel method, Agent-user Interaction with UncerTainty Awareness (AIUTA)<n>AIUTA achieves competitive performance in instance navigation against state-of-the-art methods, demonstrating great flexibility in handling user inputs.
  arXiv  Detail & Related papers  (2024-12-02T08:16:38Z)
• Towards Empathetic Conversational Recommender Systems [77.53167131692]
  We propose an empathetic conversational recommender (ECR) framework. ECR contains two main modules: emotion-aware item recommendation and emotion-aligned response generation. Our experiments on the ReDial dataset validate the efficacy of our framework in enhancing recommendation accuracy and improving user satisfaction.
  arXiv  Detail & Related papers  (2024-08-30T15:43:07Z)
• Constraining Participation: Affordances of Feedback Features in Interfaces to Large Language Models [49.74265453289855]
  Large language models (LLMs) are now accessible to anyone with a computer, a web browser, and an internet connection via browser-based interfaces. This paper examines the affordances of interactive feedback features in ChatGPT's interface, analysing how they shape user input and participation in iteration.
  arXiv  Detail & Related papers  (2024-08-27T13:50:37Z)
• Dynamic Explanation Emphasis in Human-XAI Interaction with Communication Robot [2.6396287656676725]
  DynEmph is a method for a communication robot to decide where to emphasize XAI-generated explanations with physical expressions. It predicts the effect of emphasizing certain points on a user and aims to minimize the expected difference between predicted user decisions and AI-suggested ones.
  arXiv  Detail & Related papers  (2024-03-21T16:50:12Z)
• Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems [0.0]
  This work aims to bridge the gap by developing a suggestion question generator. To generate suggestion questions, our approach involves utilizing dynamic context. We show that the dynamic contexts approach can generate better suggestion questions as compared to other prompting approaches.
  arXiv  Detail & Related papers  (2024-03-18T02:01:58Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• To be or not to be? an exploration of continuously controllable prompt engineering [21.915123121438537]
  We introduce ControlPE (Continuously Controllable Prompt Engineering) to enable finer adjustments to prompt effects. This approach harnesses the power of LoRA (Low-Rank Adaptation) to create an effect akin to prompt weighting. Our methodology involves generating specialized datasets for prompt distillation, incorporating these prompts into the LoRA model, and carefully adjusting LoRA merging weight to regulate the influence of prompts. It proves to be a promising solution for control a variety of prompts, ranging from generating short responses prompts, refusal prompts to chain-of-thought prompts.
  arXiv  Detail & Related papers  (2023-11-16T10:55:29Z)
• ASQ-IT: Interactive Explanations for Reinforcement-Learning Agents [7.9603223299524535]
  We present ASQ-IT -- an interactive tool that presents video clips of the agent acting in its environment based on queries given by the user that describe temporal properties of behaviors of interest. Our approach is based on formal methods: queries in ASQ-IT's user interface map to a fragment of Linear Temporal Logic over finite traces (LTLf), which we developed, and our algorithm for query processing is based on automata theory.
  arXiv  Detail & Related papers  (2023-01-24T11:57:37Z)
• Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy [83.61404191470126]
  We propose a new solution named I-Pro that can learn Proactive policy in the Interactive setting. Specifically, we learn the trade-off via a learned goal weight, which consists of four factors. The experimental results demonstrate I-Pro significantly outperforms baselines in terms of effectiveness and interpretability.
  arXiv  Detail & Related papers  (2022-04-07T14:11:31Z)
• Advances and Challenges in Conversational Recommender Systems: A Survey [133.93908165922804]
  We provide a systematic review of the techniques used in current conversational recommender systems (CRSs) We summarize the key challenges of developing CRSs into five directions. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI)
  arXiv  Detail & Related papers  (2021-01-23T08:53:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.